/
/
Compare Procore observation setup with what the site really raises
For safety and quality teams who ask their AI assistant to audit a Procore project's observation types, field sets and distribution.
On this page
Connector
Connect Procore, pick your AI tool and paste the prompt.
The problem
Observation setup is inherited and never checked
Types and distributions come down from the company and nobody compares them with the observations a project actually logs. Unused types, stray categories and an empty distribution stay hidden.
Without PopdockAI
- Open the project's observation types and field sets
- Check who is on the default distribution
- Scan observations to see which categories are used
- Reconcile the two lists by hand
With PopdockAI
- Types, field sets and distribution are read in one pass
- Categories in use are compared with project types
- Empty distributions and ineligible members are flagged
- Nothing in the configuration is edited
The prompt
Use this prompt
Copy it into any AI tool connected to PopdockAI. Swap the values in braces for your own.
**Objective:** Audit the observation configuration of {project-name}: the types in use, configurable field sets and who is on the default distribution.
**Step 1: Resolve the project**
Call `procore-get-viewer-documents-accessible-tools` with `project-name` equal to {project-name} to resolve the project id. If nothing matches, retry with `project-name.contains`. If more than one project matches, list them with their ids and stop and ask which one. If the user named a Procore company, pass it in the `company` parameter on every call.
**Step 2: Read the setup**
Call `procore-get-project-observation-types`, `procore-get-observations-category-configurable-field-sets`, `procore-get-observations-default-distribution` and `procore-get-observations-potential-distribution-members` with the `project-id`.
**Step 3: Compare with practice**
Call `procore-get-observations-items` with the `project-id` and compare the categories in use with the project's types.
**Step 4: Report**
Output the types, field sets and default distribution, then findings: types never used, categories in use that are not project types, an empty default distribution, and people on the distribution who are not eligible members.
**Rules & Guidelines:**
* This prompt is read-only. Never call any create, update, delete, bulk, send, restore or sync tool (for example `procore-create-rfi`, `procore-update-punch-item`, `procore-delete-incident` or `procore-send-punch-item-email`).
* Report only what the tools return. Do not guess missing dates, amounts or names; mark them as missing.
* Counts come from the records returned, and `max-records` caps each call, so say when a call returned its cap and the picture may be partial.
**Validation:**
* If the project cannot be resolved, stop and say so. Do not read records from an unresolved project.
* If the main read returns nothing, say the project has none and stop. Do not fill the gap with assumptions.
Who it's for
One answer, three teams that use it
Safety coordinators
Make sure the right people hear
Check that the default distribution is not empty and holds eligible members.
Is the default distribution for observations on Riverside Tower empty or out of date?
Quality managers
Remove types nobody uses
See which observation types were never raised, so the list your crews pick from stays short.
Which observation types on Contoso Warehouse have never been used?
Project engineers
Align categories with the project
Find categories being used that are not part of the project's types.
Compare the observation categories in use on Fabrikam Depot with its configured types.
How it works
What PopdockAI does when you ask
You name the project and your AI assistant reads its observation setup and its observations. It reports the differences and leaves every setting as it is.
Ask
You name the project to audit.
Resolve
It finds the one matching project, or asks which one you mean.
Read
It reads the project's observation types, field sets and distribution, then its observations.
Report
You get the setup and findings on unused types, stray categories and distribution gaps.
What PopdockAI provides
The tools behind the answer
Ready made tools for Procore and one secure connection to your AI tool. No code, no exports.
procore-get-viewer-documents-accessible-tools
procore-get-project-observation-types
procore-get-observations-category-configurable-field-sets
procore-get-observations-default-distribution
procore-get-observations-potential-distribution-members
procore-get-observations-items
This report is built from Get data tools only. PopdockAI applies the row, field and parameter rules your admin sets, and every query is written to the audit trail.
The outcome
Observation setup that matches the site
Related use cases
More ways to put this data to work
One prompt template with infinite possibilities.
Your AI assistant adapts its approach, tone, and capabilities to match each unique context while you maintain a single, manageable workflow.
Join forward-thinking companies that are transforming their operations with intelligent, secure AI automation.

.webp)
